Classification of Traversable Surfaces for Navigation Combining Multiple Cues Toward a Visual-Based Learning System - ENSTA Paris - École nationale supérieure de techniques avancées Paris Accéder directement au contenu
Communication Dans Un Congrès Année : 2010

Classification of Traversable Surfaces for Navigation Combining Multiple Cues Toward a Visual-Based Learning System

Toby Low
  • Fonction : Auteur correspondant
  • PersonId : 964960

Connectez-vous pour contacter l'auteur
Antoine Manzanera

Résumé

This paper describes a vision-based ground-plane classification system for autonomous indoor mobile-robot that takes advantage of the synergy in combining together multiple visual-cues. A priori knowledge of the environment is important in many biological systems, in parallel with their mutually beneficial reactive systems. As such, a learning model approach is taken here for the classification of the ground/object space, initialised through a new Distributed-Fusion (D-Fusion) method that captures colour and textural data using Superpixels. A Markov Random Field (MRF) network is then used to classify, regularise, employ a priori constraints, and merge additional ground/object information provided by other visual cues (such as motion) to improve classification images. The developed system can classify indoor test-set ground-plane surfaces with an average true-positive to false-positive rate of 90.92% to 7.78% respectively on test-set data. The system has been designed in mind to fuse a variety of different visual-cues. Consequently it can be customised to fit different situations and/or sensory architectures accordingly.
Fichier principal
Vignette du fichier
ICARCV2010.pdf (354.85 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01130908 , version 1 (12-03-2015)

Identifiants

  • HAL Id : hal-01130908 , version 1

Citer

Toby Low, Antoine Manzanera. Classification of Traversable Surfaces for Navigation Combining Multiple Cues Toward a Visual-Based Learning System. International Conference on Control, Automation, Robotics and Vision, (ICARCV), Dec 2010, Singapour, Singapore. ⟨hal-01130908⟩

Collections

ENSTA ENSTA_U2IS
39 Consultations
71 Téléchargements

Partager

Gmail Facebook X LinkedIn More